Papers by Andrea Pedrotti
Stress-testing Machine Generated Text Detection: Shifting Language Models Writing Style to Fool Detectors (2025.findings-acl)
Copied to clipboard
Andrea Pedrotti, Michele Papucci, Cristiano Ciaccio, Alessio Miaschi, Giovanni Puccetti, Felice Dell’Orletta, Andrea Esuli
| Challenge: | Recent advances in Generative AI and Large Language Models (LLMs) have enabled the creation of highly realistic synthetic content, raising concerns about the potential for malicious use, such as misinformation and manipulation. |
| Approach: | They evaluate the resilience of state-of-the-art MGT detectors to linguistically informed adversarial attacks by using Direct Preference Optimization to shift the MGT style toward human-written text. |
| Outcome: | The proposed pipeline fine-tunes language models to shift the MGT style toward human-written text (HWT) it obtains generations more challenging to detect by current models, and shows that detectors can be easily fooled with relatively few examples, resulting in a significant drop in detecting performances. |
How Humans and LLMs Organize Conceptual Knowledge: Exploring Subordinate Categories in Italian (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies on hierarchical organization of categories focused on basic-1 . but, words at the subordinate level are crucial for effective communication in specialized domains. |
| Approach: | They analyze a psycholinguistic dataset of human-generated exemplars for 187 concrete words . they then evaluate whether textual and vision LLMs produce meaningful exemplar . |
| Outcome: | The results show that human-generated exemplars perform poorly in three key tasks . the results highlight the potential of using AI-generated categories in psycholinguistic research . |